scholarly journals Predicting onset, progression, and clinical subtypes of Parkinson disease using machine learning

2018 ◽  
Author(s):  
Faraz Faghri ◽  
Sayed Hadi Hashemi ◽  
Hampton Leonard ◽  
Sonja W. Scholz ◽  
Roy H. Campbell ◽  
...  
Keyword(s):  
Machine Learning ◽  
Parkinson Disease ◽  
Disease Progression ◽  
Clinical Care ◽  
Age At Onset ◽  
Unmet Need ◽  
Clinical Manifestations ◽  
Supervised Machine Learning ◽  
Distinct Disease ◽  
Disease Subtypes

AbstractBackgroundThe clinical manifestations of Parkinson disease are characterized by heterogeneity in age at onset, disease duration, rate of progression, and constellation of motor versus nonmotor features. Due to these variable presentations, counseling of patients about their individual risks and prognosis is limited. There is an unmet need for predictive tests that facilitate early detection and characterization of distinct disease subtypes as well as improved, individualized predictions of the disease course. The emergence of machine learning to detect hidden patterns in complex, multi-dimensional datasets provides unparalleled opportunities to address this critical need.Methods and FindingsWe used unsupervised and supervised machine learning approaches for subtype identification and prediction. We used machine learning methods on comprehensive, longitudinal clinical data from the Parkinson Disease Progression Marker Initiative (PPMI) (n=328 cases) to identify patient subtypes and to predict disease progression. The resulting models were validated in an independent, clinically well-characterized cohort from the Parkinson Disease Biomarker Program (PDBP) (n=112 cases). Our analysis distinguished three distinct disease subtypes with highly predictable progression rates, corresponding to slow, moderate and fast disease progressors. We achieved highly accurate projections of disease progression four years after initial diagnosis with an average Area Under the Curve of 0.93 (95% CI: 0.96 ± 0.01 for PDvec1, 0.87 ± 0.03 for PDvec2, and 0.96 ± 0.02 for PDvec3). We have demonstrated robust replication of these findings in the independent validation cohort.ConclusionsThese data-driven results enable clinicians to deconstruct the heterogeneity within their patient cohorts. This knowledge could have immediate implications for clinical trials by improving the detection of significant clinical outcomes that might have been masked by cohort heterogeneity. We anticipate that machine learning models will improve patient counseling, clinical trial design, allocation of healthcare resources and ultimately individualized clinical care.

Machine Learning Approaches to Retrieve High-Quality, Clinically Relevant, Evidence from the Biomedical Literature: A Systematic Review (Preprint)

2021 ◽  
Author(s):  
Wael Abdelkader ◽  
Tamara Navarro ◽  
Rick Parrish ◽  
Chris Cotoi ◽  
Federico Germini ◽  
...  
Keyword(s):  
Machine Learning ◽  
Systematic Review ◽  
Strong Evidence ◽  
Clinical Care ◽  
Biomedical Literature ◽  
Supervised Machine Learning ◽  
Machine Learning Techniques ◽  
Learning Approaches ◽  
High Quality ◽  
Applied Machine Learning

BACKGROUND The rapid growth of the biomedical literature makes identifying strong evidence a time-consuming task. Applying machine learning to the process could be a viable solution that limits effort while maintaining accuracy. OBJECTIVE To summarize the nature and comparative performance of machine learning approaches that have been applied to retrieve high-quality evidence for clinical consideration from the biomedical literature. METHODS We conducted a systematic review of studies that applied machine learning techniques to identify high-quality clinical articles in the biomedical literature. Multiple databases were searched to July 2020. Extracted data focused on the applied machine learning model, steps in the development of the models, and model performance. RESULTS From 3918 retrieved studies, 10 met our inclusion criteria. All followed a supervised machine learning approach and applied, from a limited range of options, a high-quality standard for the training of their model. The results show that machine learning can achieve a sensitivity of 95% while maintaining a high precision of 86%. CONCLUSIONS Applying machine learning to distinguish studies with strong evidence for clinical care has the potential to decrease the workload of manually identifying these. The evidence base is active and evolving. Reported methods were variable across the studies but focused on supervised machine learning approaches. Performance may improve by applying more sophisticated approaches such as active learning, auto-machine learning, and unsupervised machine learning approaches.

scholarly journals Genetic risk of Parkinson disease and progression:

2019 ◽  
Vol 5 (4) ◽  
pp. e348 ◽  
Author(s):  
Hirotaka Iwaki ◽  
Cornelis Blauwendraat ◽  
Hampton L. Leonard ◽  
Ganqiang Liu ◽  
Jodi Maple-Grødem ◽  
...  
Keyword(s):  
Parkinson Disease ◽  
Disease Progression ◽  
Disease Risk ◽  
Age At Onset ◽  
Motor Symptom ◽  
European Ancestry ◽  
Sleep Behavior ◽  
Intronic Region ◽  
Risk Variants ◽  
Faster Development

ObjectiveTo determine if any association between previously identified alleles that confer risk for Parkinson disease and variables measuring disease progression.MethodsWe evaluated the association between 31 risk variants and variables measuring disease progression. A total of 23,423 visits by 4,307 patients of European ancestry from 13 longitudinal cohorts in Europe, North America, and Australia were analyzed.ResultsWe confirmed the importance of GBA on phenotypes. GBA variants were associated with the development of daytime sleepiness (p.N370S: hazard ratio [HR] 3.28 [1.69–6.34]) and possible REM sleep behavior (p.T408M: odds ratio 6.48 [2.04–20.60]). We also replicated previously reported associations of GBA variants with motor/cognitive declines. The other genotype-phenotype associations include an intergenic variant near LRRK2 and the faster development of motor symptom (Hoehn and Yahr scale 3.0 HR 1.33 [1.16–1.52] for the C allele of rs76904798) and an intronic variant in PMVK and the development of wearing-off effects (HR 1.66 [1.19–2.31] for the C allele of rs114138760). Age at onset was associated with TMEM175 variant p.M393T (−0.72 [−1.21 to −0.23] in years), the C allele of rs199347 (intronic region of GPNMB, 0.70 [0.27–1.14]), and G allele of rs1106180 (intronic region of CCDC62, 0.62 [0.21–1.03]).ConclusionsThis study provides evidence that alleles associated with Parkinson disease risk, in particular GBA variants, also contribute to the heterogeneity of multiple motor and nonmotor aspects. Accounting for genetic variability will be a useful factor in understanding disease course and in minimizing heterogeneity in clinical trials.

scholarly journals Practice Parameter: Diagnosis and prognosis of new onset Parkinson disease (an evidence-based review)

Neurology ◽  
2006 ◽  
Vol 66 (7) ◽  
pp. 968-975 ◽  
Author(s):  
O. Suchowersky ◽  
S. Reich ◽  
J. Perlmutter ◽  
T. Zesiewicz ◽  
G. Gronseth ◽  
...  
Keyword(s):  
Parkinson Disease ◽  
Disease Progression ◽  
Clinical Features ◽  
Predictive Factors ◽  
Age At Onset ◽  
Future Research ◽  
Evidence Based ◽  
Level Of Evidence ◽  
Parkinsonian Syndromes ◽  
Olfactory Testing

Objective: To define key issues in the diagnosis of Parkinson disease (PD), to define features influencing progression, and to make evidence-based recommendations. Two clinical questions were identified: 1) Which clinical features and diagnostic modalities distinguish PD from other parkinsonian syndromes? 2) Which clinical features predict rate of disease progression?Methods: Systematic review of the literature was completed. Articles were classified according to a four-tiered level of evidence scheme. Recommendations were based on the evidence.Results and Conclusions: 1. Early falls, poor response to levodopa, symmetry of motor manifestations, lack of tremor, and early autonomic dysfunction are probably useful in distinguishing other parkinsonian syndromes from Parkinson disease (PD). 2. Levodopa or apomorphine challenge and olfactory testing are probably useful in distinguishing PD from other parkinsonian syndromes. 3. Predictive factors for more rapid motor progression, nursing home placement, and shorter survival time include older age at onset of PD, associated comorbidities, presentation with rigidity and bradykinesia, and decreased dopamine responsiveness. Future research into methods for earlier and more accurate diagnosis of the disease and identification and clarification of predictive factors of rapid disease progression is warranted.

scholarly journals Diffusion Histology Imaging Combining Diffusion Basis Spectrum Imaging (DBSI) and Machine Learning Improves Detection and Classification of Glioblastoma Pathology

2019 ◽  
Author(s):  
Zezhong Ye ◽  
Richard L. Price ◽  
Xiran Liu ◽  
Joshua Lin ◽  
Qingsong Yang ◽  
...  
Keyword(s):  
Machine Learning ◽  
Tumor Necrosis ◽  
Surgical Planning ◽  
Learning Algorithm ◽  
Unmet Need ◽  
Supervised Machine Learning ◽  
Tumor Infiltration ◽  
Apparent Diffusion ◽  
High Cellularity ◽  
Spectrum Imaging

AbstractPurposeGlioblastoma (GBM) is one of the deadliest cancers with no cure. While conventional MRI has been widely adopted for examining GBM clinically, accurate neuroimaging assessment of tumor histopathology for improved diagnosis, surgical planning, and treatment evaluation, remains an unmet need in the clinical management of GBMs.Experimental DesignWe employ a novel Diffusion Histology Imaging (DHI) approach, combining diffusion basis spectrum imaging (DBSI) and machine learning, to detect, differentiate, and quantify areas of high cellularity, tumor necrosis, and tumor infiltration in GBM.ResultsGd-enhanced T1W or hyper-intense FLAIR failed to reflect the morphological complexity underlying tumor in GBM patients. Contrary to the conventional wisdom that apparent diffusion coefficient (ADC) negatively correlates with increased tumor cellularity, we demonstrate disagreement between ADC and histologically confirmed tumor cellularity in glioblastoma specimens, whereas DBSI-derived restricted isotropic diffusion fraction positively correlated with tumor cellularity in the same specimens. By incorporating DBSI metrics as classifiers for a supervised machine learning algorithm, we accurately predicted high tumor cellularity, tumor necrosis, and tumor infiltration with 87.5%, 89.0% and 93.4% accuracy, respectively.ConclusionOur results suggest that DHI could serve as a favorable alternative to current neuroimaging techniques for guiding biopsy or surgery as well as monitoring therapeutic response in the treatment of glioblastoma.Translational RelevanceCurrent clinical diagnosis, surgical planning, and assessment of treatment response for GBM patients relies heavily on gadolinium-enhanced T1-weighted MRI, which is non-specific for tumor growth and merely reflects a disrupted blood-brain barrier. The complex tumor microenvironment and spatial heterogeneity make GBM difficult to characterize using current clinical imaging modalities. In this study, we developed a novel imaging technique to characterize and accurately predict key histological features of GBM - high tumor cellularity, tumor necrosis, and tumor infiltration. While further validation in a larger cohort of patients is needed, the current proof-of-concept approach could provide a solution to resolve important clinical questions such as the identification of true tumor progression vs. pseudoprogression or radiation necrosis.

scholarly journals FBN1 Mutation Screening in a Marfan Syndrome Patient

2017 ◽  
Vol 3 (1) ◽  
Author(s):  
Amallia Setyawati ◽  
Nani Maharani ◽  
Sultana Faradz ◽  
Gerard Pals ◽  
Sodiqur Rifqi ◽  
...  
Keyword(s):  
Disulfide Bonds ◽  
Transforming Growth Factor ◽  
Early Recognition ◽  
Clinical Care ◽  
Mutation Screening ◽  
Age At Onset ◽  
Clinical Manifestations ◽  
Missense Mutations ◽  
Arm Span ◽  
Wide Range

Background : MFS is characterized by variable clinical manifestations mainly in cardiovascular, ocular, and skeletal systems. The major encoding gene of structural constituent of extracellular microfibrils is Fibrillin-1 (FBN1). Approximately 90% of MFS cases are caused by mutations in the FBN1 gene (15q21.1) and the other second is TGFBR2 (3p22) gene. Methods : The UMD database, Ensemble database and VUmc DNA Laboratory database of FBN1 mutations and polymorphisms were used to evaluate the DNA variations. For paternity testing, the PowerPlex system (Promega Corp. USA) was used. A 30-years old was being admitted to the hospital. CKMB and Troponin C serial. A CT angiography was performed and revealed a long type 1 aortic dissection until proximal of bifurcation, the arm span-height ratio is 1.10, high myopia, arachnodactily, positive thumb signs and wrist signs, joint laxity articulation genu, and history of spontaneous pneumothorax. Identified, his mother, two sisters and one brother are clinically MFS. Results : Genetic testing of FBN1 showed a substation at exon 15 of FBN1, c.1924G>T. Discussion: In missense mutations substituting or creating cysteine, the probability of ectopia lentis is significantly higher compared to other missense mutations. The EGF domains are interrupted by seven transforming growth factor (TGF)-binding protein domains characterized by 8 cysteine residues involved in intra-domain disulfide bonds. Conclusion : Untreated, life expectancy of patients with MFS is considerably reduced. Clinical care is complicated by variable age at onset and the wide range of severity of aortic features. Early recognition of affected status hopefully will lead to early prevention of complications that may follow.

Exploring the Use of Machine Learning to Automate the Qualitative Coding of Church-related Tweets

2020 ◽  
Vol 14 (2) ◽  
pp. 140-159
Author(s):  
Anthony-Paul Cooper ◽  
Emmanuel Awuni Kolog ◽  
Erkki Sutinen
Keyword(s):  
Machine Learning ◽  
Online Community ◽  
High Volume ◽  
Machine Learning Algorithms ◽  
Supervised Machine Learning ◽  
Social Media Data ◽  
Twitter Data ◽  
Resource Intensity ◽  
Media Data ◽  
Better Than

This article builds on previous research around the exploration of the content of church-related tweets. It does so by exploring whether the qualitative thematic coding of such tweets can, in part, be automated by the use of machine learning. It compares three supervised machine learning algorithms to understand how useful each algorithm is at a classification task, based on a dataset of human-coded church-related tweets. The study finds that one such algorithm, Naïve-Bayes, performs better than the other algorithms considered, returning Precision, Recall and F-measure values which each exceed an acceptable threshold of 70%. This has far-reaching consequences at a time where the high volume of social media data, in this case, Twitter data, means that the resource-intensity of manual coding approaches can act as a barrier to understanding how the online community interacts with, and talks about, church. The findings presented in this article offer a way forward for scholars of digital theology to better understand the content of online church discourse.

Mol2vec: Unsupervised Machine Learning Approach with Chemical Intuition

2017 ◽  
Author(s):  
Sabrina Jaeger ◽  
Simone Fulle ◽  
Samo Turk
Keyword(s):  
Machine Learning ◽  
Language Processing ◽  
Supervised Machine Learning ◽  
Learning Approach ◽  
Learning Approaches ◽  
Unsupervised Machine Learning ◽  
Feature Representations ◽  
Machine Learning Approach ◽  
The Individual ◽  
Vector Representations

Inspired by natural language processing techniques we here introduce Mol2vec which is an unsupervised machine learning approach to learn vector representations of molecular substructures. Similarly, to the Word2vec models where vectors of closely related words are in close proximity in the vector space, Mol2vec learns vector representations of molecular substructures that are pointing in similar directions for chemically related substructures. Compounds can finally be encoded as vectors by summing up vectors of the individual substructures and, for instance, feed into supervised machine learning approaches to predict compound properties. The underlying substructure vector embeddings are obtained by training an unsupervised machine learning approach on a so-called corpus of compounds that consists of all available chemical matter. The resulting Mol2vec model is pre-trained once, yields dense vector representations and overcomes drawbacks of common compound feature representations such as sparseness and bit collisions. The prediction capabilities are demonstrated on several compound property and bioactivity data sets and compared with results obtained for Morgan fingerprints as reference compound representation. Mol2vec can be easily combined with ProtVec, which employs the same Word2vec concept on protein sequences, resulting in a proteochemometric approach that is alignment independent and can be thus also easily used for proteins with low sequence similarities.

Sign in / Sign up

Export Citation Format

Share Document